Mark Backman
Mark Backman
Is this still an issue? In nearly 8 additional months of testing, I haven't hit this issue. I'm inclined to close this out unless there's a repro case and instructions...
I see this too. We'll fix it.
Yes, I have noticed this too. We will look into it.
We're working on a fix here: https://github.com/pipecat-ai/pipecat/pull/2091. This will be in the upcoming Pipecat release.
Do you hear this crackling consistently? I've just tested using the [34 foundational example](https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/34-audio-recording.py) and I really can't hear any crackling. In scrutinizing the audio, I thought I might have...
Also, I meant to close this one out as this issue is not fixed with 0.0.74.
@aristid one option is to keep a streaming version and non-streaming version. We have other examples of this. For example `CartesiaTTSService` is the websocket API service and `CartesiaHttpTTSService` is the...
> should I make a pull request? Yes, please! 🙌 > GoogleStreamingTTSService, to keep the http version working? It really is much faster, making using standard Gemini feasible instead of...
Thanks for the submission! This generally looks good. If you can remove the LLM model env var and arg all together, I think this is good to go.
@sanjeed5 pinging about my previous comment so we can get this merged.